Accelerated gradient algorithm for RBF neural network

Generalized M-sparse algorithms for constructing fault tolerant RBF networks

In the construction process of radial basis function (RBF) networks, two common crucial issues arise: the selection of RBF centers and the effective utilization of the given source without encountering the overfitting problem. Another important issue is the fault tolerant capability. That is, when noise or faults exist in a trained network, it is crucial that the network's performance does not undergo significant deterioration or decrease. However, without employing a fault tolerant procedure, a trained RBF network may exhibit significantly poor performance. Unfortunately, most existing algorithms are unable to simultaneously address all of the aforementioned issues. This paper proposes fault tolerant training algorithms that can simultaneously select RBF nodes and train RBF output weights. Additionally, our algorithms can directly control the number of RBF nodes in an explicit manner, eliminating the need for a time-consuming procedure to tune the regularization parameter and achieve the target RBF network size. Based on simulation results, our algorithms demonstrate improved test set performance when more RBF nodes are used, effectively utilizing the given source without encountering the overfitting problem. This paper first defines a fault tolerant objective function, which includes a term to suppress the effects of weight faults and weight noise. This term also prevents the issue of overfitting, resulting in better test set performance when more RBF nodes are utilized. With the defined objective function, the training process is designed to solve a generalized M-sparse problem by incorporating an ℓ0-norm constraint. The ℓ0-norm constraint allows us to directly and explicitly control the number of RBF nodes. To address the generalized M-sparse problem, we introduce the noise-resistant iterative hard thresholding (NR-IHT) algorithm. The convergence properties of the NR-IHT algorithm are subsequently discussed theoretically. To further enhance performance, we incorporate the momentum concept into the NR-IHT algorithm, referring to the modified version as "NR-IHT-Mom". Simulation results show that both the NR-IHT algorithm and the NR-IHT-Mom algorithm outperform several state-of-the-art comparison algorithms.

Learning active subspaces and discovering important features with Gaussian radial basis functions neural networks

Providing a model that achieves a strong predictive performance and is simultaneously interpretable by humans is one of the most difficult challenges in machine learning research due to the conflicting nature of these two objectives. To address this challenge, we propose a modification of the radial basis function neural network model by equipping its Gaussian kernel with a learnable precision matrix. We show that precious information is contained in the spectrum of the precision matrix that can be extracted once the training of the model is completed. In particular, the eigenvectors explain the directions of maximum sensitivity of the model revealing the active subspace and suggesting potential applications for supervised dimensionality reduction. At the same time, the eigenvectors highlight the relationship in terms of absolute variation between the input and the latent variables, thereby allowing us to extract a ranking of the input variables based on their importance to the prediction task enhancing the model interpretability. We conducted numerical experiments for regression, classification, and feature selection tasks, comparing our model against popular machine learning models, the state-of-the-art deep learning-based embedding feature selection techniques, and a transformer model for tabular data. Our results demonstrate that the proposed model does not only yield an attractive prediction performance compared to the competitors but also provides meaningful and interpretable results that potentially could assist the decision-making process in real-world applications. A PyTorch implementation of the model is available on GitHub at the following link.1.

Tomato plant leaf disease segmentation and multiclass disease detection using hybrid optimization enabled deep learning

Production of crops is increasing day by day in agriculture sectors. The insecurity of food is a main reason of plant disease and is a main global issue that humans face these days. With the design of contemporary environmental agriculture, more focus is devised for yielding the crop and elevating its quality. The occurrence of crops has elevated in years and the kind of disease has become more and more complex. The disease in plants and the pernicious insects are the major risks in agriculture field. Thus, earlier discovery and treatment of this disease are imperative. The major design of Deep Learning (DL) model helped in detecting the plant disease and grants a dynamic tool with accurate results. This paper presents DL-assisted technique for detecting and classifying the tomato disease and used deep batch-normalized eLu Alex Net (DbneAlexnet) for classifying the tomato plant leaves. Initially, tomato plant leaf images are taken as an input from specific dataset represented and it is subjected to preprocessing phase to eliminate unwanted distortions using anisotropic filtering. Then, the segmentation is carried out using U-net, which is trained by Gradient-Golden search optimization (Gradient-GSO) Algorithm and it is incorporation of both Golden search optimization (GSO) and Gradient concept. Thereafter the segmented image is given to image augmentation process, where position augmentation and color augmentation are considered. Finally, the multiclass plant leaf disease is classified using DbneAlexnet and is trained using proposed Gradient Jaya- Golden search optimization (GJ-GSO). Here, the GJ-GSO is devised with the integration of Gradient concept, Jaya algorithm, and GSO algorithm. The proposed GJ-GSO-based DbneAlexnet outperformed highest accuracy of 92.4%, True positive rate (TPR) of 91.9%, True negative rate (TNR) of 92.2% and smallest False Positive Rate (FPR) of 0.078. Hence, the technique with unified segmentation and classification is effectual for identifying the plant disease and the empirical research verifies the benefits of the developed model.

Introduction of Materials Genome Technology and Its Applications in the Field of Biomedical Materials

Traditional research and development (R&D) on biomedical materials depends heavily on the trial and error process, thereby leading to huge economic and time burden. Most recently, materials genome technology (MGT) has been recognized as an effective approach to addressing this problem. In this paper, the basic concepts involved in the MGT are introduced, and the applications of MGT in the R&D of metallic, inorganic non-metallic, polymeric, and composite biomedical materials are summarized; in view of the existing limitations of MGT for R&D of biomedical materials, potential strategies are proposed on the establishment and management of material databases, the upgrading of high-throughput experimental technology, the construction of data mining prediction platforms, and the training of relevant materials talents. In the end, future trend of MGT for R&D of biomedical materials is proposed.

An RBF neural network based on improved black widow optimization algorithm for classification and regression problems

Introduction

Regression and classification are two of the most fundamental and significant areas of machine learning.

Methods

In this paper, a radial basis function neural network (RBFNN) based on an improved black widow optimization algorithm (IBWO) has been developed, which is called the IBWO-RBF model. In order to enhance the generalization ability of the IBWO-RBF neural network, the algorithm is designed with nonlinear time-varying inertia weight.

Discussion

Several classification and regression problems are utilized to verify the performance of the IBWO-RBF model. In the first stage, the proposed model is applied to UCI dataset classification, nonlinear function approximation, and nonlinear system identification; in the second stage, the model solves the practical problem of power load prediction.

Results

Compared with other existing models, the experiments show that the proposed IBWO-RBF model achieves both accuracy and parsimony in various classification and regression problems.